Object tracking device

Abstract

A system includes a microcontroller, one or more sensors affixed to an object, and memory storing one or more programs including instructions for receiving and storing first sensor data from the one or more sensors in response to motion of the object, determining whether the first sensor data meets a first threshold, in accordance with a determination that the first sensor data meets the first threshold: receiving and storing second sensor data from the one or more sensors in response to subsequent motion of the object for as long as the second sensor data meets a second threshold, performing pattern recognition on the second sensor data, and identifying a first position of the object based on the pattern recognition of the second sensor data.

What is claimed is: 
     
       1. A method comprising:
 at a system including a microcontroller, a plurality of sensors in proximity to an object, and memory storing programs for execution by the microcontroller:
 receiving first data from the plurality of sensors; 
 identifying a position of the object based on performing a pattern recognition on the first data; and 
 in accordance with a determination that the position matches a predetermined position:
 receiving second data from at least one sensor of the plurality of sensors, wherein the at least one sensor is configured to detect tension or stress levels on a surface of the object; and 
 encoding the second data to correspond to a configuration of the object. 
 
 
 
     
     
       2. The method of  claim 1 , wherein the configuration corresponds to a shape of the object. 
     
     
       3. The method of  claim 1 , wherein the object is a hand and the second data is used to detect tension on palm of the hand or detect if the hand is in a first or has fingers extended. 
     
     
       4. The method of  claim 1 , wherein the object is a hand and the plurality of sensors includes a first sensor affixed to a first finger of the hand and a second sensor affixed to a second finger of the object. 
     
     
       5. The method of  claim 1 , wherein the object is hand-shaped and the plurality of sensors includes a first sensor and a second sensor affixed to different digits of the object. 
     
     
       6. The method of  claim 1 , wherein the configuration corresponds to a static positional gesture of the object. 
     
     
       7. The method of  claim 6 , wherein the object is a user's hand and the static positional gesture corresponds to the user raising and holding the hand still, the configuration further includes a motion that corresponds to the user spreading fingers of the hand apart. 
     
     
       8. The method of  claim 1 , wherein the object is a user's hand and the configuration of the object corresponds to a movement of the hand while simultaneously holding fingers in a predetermined position. 
     
     
       9. The method of  claim 1 , wherein the object is a user's hand and the configuration of the object corresponds to an operation selected from the group consisting of: swatting, throwing, or crossing out. 
     
     
       10. The method of  claim 1 , further comprising determining an orientation of the object based on the configuration of the object. 
     
     
       11. The method of  claim 10 , wherein the orientation is a tilt orientation. 
     
     
       12. The method of  claim 1 , wherein the first data is obtained from a first set of sensors of the plurality of sensors and the second data is obtained from a second set of sensors of the plurality of sensors, and wherein the first set of sensors is distinct from the second set of sensors. 
     
     
       13. The method of  claim 1 , further comprising controlling a wirelessly connected device based on the configuration of the object. 
     
     
       14. The method of  claim 1 , wherein the plurality of sensors includes one or more sensors selected from the group consisting of: magnetometers, gyroscopes, inertial sensors, accelerometers and electro-myograms. 
     
     
       15. The method of  claim 14 , wherein:
 the magnetometers are configured to measure an orientation of the object relative to earth's magnetic field; 
 the gyroscopes are configured to measure changes in angular orientation of the object in one or more axes; 
 the accelerometers are configured to measure changes in movement of the object in one or more axes; and 
 the electro-myograms are configured to measure electrical signals produced during muscle contractions of the object. 
 
     
     
       16. The method of  claim 1 , wherein the pattern recognition includes one or more recognition layers including at least one of: K-Nearest Neighbors, neural networks, decision trees, or hidden Markov model. 
     
     
       17. The method of  claim 1 , wherein the plurality of sensors includes a bend sensor configured to detect a bend position of a finger of a user of the object. 
     
     
       18. The method of  claim 1 , wherein the object is a wearable HMI device, and wherein the plurality of sensors includes a bend sensor positioned in the wearable HMI device in proximity to a finger or hand joint or a muscle of a user of the wearable HMI device, such that any motion of such joint or muscle causes deformation of the bend sensor, resulting in the bend sensor outputting a respective analog signal representative of extent of the deformation. 
     
     
       19. The method of  claim 1 , wherein object is a user's hand, the plurality of sensors includes four bend sensors placed on a dorsal side of a proximal interphalangeal joint of the object, and one bend sensor placed between a thumb and an index finger of the user. 
     
     
       20. A wearable gesture control interface apparatus comprising:
 a plurality of sensors affixed to an object, one or more microcontrollers and memory storing one or more programs to be executed by the one or more microcontrollers, the one or more programs including instructions for:
 receiving first data from the plurality of sensors; 
 identifying a position of the object based on performing a pattern recognition on the first data; and 
 in accordance with a determination that the position matches a predetermined position:
 receiving second data from at least one sensor of the plurality of sensors, wherein the at least one sensor is configured to detect tension or stress levels on the object; and 
 encoding the second data to correspond to a configuration of the object.